Aircover.ai

View saved version →

---
name: aircover-mutual-action-plan
description: Generate a completed Mutual Action Plan (MAP) spreadsheet for a deal, pulling the account, opportunity, sponsors, target go-live date, and deal progress from the Aircover Production account and filling the team's standard MAP template. Use this whenever someone says "build a mutual action plan", "run the MAP", "make a MAP for [company]", "close plan", or "joint action plan", or wants a deal turned into the shared roadmap spreadsheet, even if they do not name the template.
---

# Aircover Mutual Action Plan

Turn a live Aircover deal into a completed Mutual Action Plan: the shared, dated
roadmap from discovery to go-live. The skill keeps the team's standard 17-step
playbook as the backbone and grounds it in real deal data (account, opportunity,
sponsors, close date, current progress, agreed next steps). Sourced values render in
black; anything the data cannot supply stays a grey placeholder so the rep sees

> **This document is customer-facing.** The MAP is shared and reviewed with the
> customer. Every cell must be value-add for both sides. Write the substance of
> what was agreed (objectives, success criteria, decisions, mutual next steps),
> never internal deal commentary. No MEDDPICC/qualification labels, no coaching or
> gap language (for example "captured across 2 calls", "still to be established",
> "process mapped", "X is the economic buyer", "we still need to extract Y"), and
> nothing that reads as the seller's private plan. If you would not say it to the
> customer's face, it does not go in a cell. See "Writing customer-facing content"
> below.
what to finish.

## Bundled resources
- `config.json` - everything org-specific: environment, how to find the agent, the template filename, the cell map, value colours, and status colours. Change this, not the code, to retarget the skill. The engine reads it automatically.
- `assets/Mutual_Action_Plan_TEMPLATE.xlsx` - the team template. Holds all styling, the Status dropdown, and the `=$F$7-Fn` due-date formulas. Do not rebuild it; fill it.
- `scripts/fill_map.py` - template-agnostic engine. Reads `config.json`, writes only the cells you supply, preserves everything else, recolours Status cells when status changes, and writes Go-Live as a real date so all due dates recalculate. Requires openpyxl.
- `references/field_source_map.md` - which Aircover field feeds which cell, and how to infer status.
- `references/example_values.json` - a worked values file.
- `README.md` - install and the three things a new customer changes. Read it if you are forking this for another org.

Copy the script, config, and template into your working directory first:
```
cp "$SKILL_DIR/scripts/fill_map.py" .
cp "$SKILL_DIR/config.json" .
cp "$SKILL_DIR/assets/Mutual_Action_Plan_TEMPLATE.xlsx" .
```

## Requirements
- The **Aircover Production** connector (api.aircover.ai) must be connected. Confirm it before running: Production and Staging share tool names, and an "agent not found" error usually means you are pointed at the wrong environment.
- Code execution / file creation on.
- `openpyxl` available in the host runtime. If it is unavailable, explain the missing dependency and stop before writing an output file; do not install packages silently.

## Configuration
All of this lives in `config.json`. Edit that file to retarget the skill; the engine and run order do not change.
- **Environment:** Production, api.aircover.ai. App host: app.aircover.ai.
- **Agent:** discovered at runtime. `config.agent.pinned_template_id` is null, so the skill calls `list_agents` and matches on `config.agent.category` ("qualification") and `config.agent.title_keywords`. To lock a specific agent, set `pinned_template_id` and discovery is skipped. Always join results on the entry `title`, never the positional key, so a rebuilt agent still works.
- **Template + layout:** `config.template.file`, the sheet name, the overview cell map, the action-item columns and row range, and 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 7 — file references are metadata, not package contents.

View saved version →

---
name: path-to-quota
description: Build a personalized end-of-quarter pipeline strategy from Aircover meeting data, CRM deal stages, MEDDPICC qualification scoring, and Deal Readiness Scorecard (close mechanics). Prompts for quota and EOQ date, finds all customer meetings in the quarter, prioritizes deals by qualification depth, close readiness, and meeting momentum, and delivers a .docx close plan with embedded charts, per-deal strategies, and next steps. Use this when someone says "path to quota", "how do I hit my number", "quarter close plan", "pipeline strategy", "what deals should I focus on", or wants a plan to close their open pipeline.
---

# Path to Quota

Build an actionable end-of-quarter pipeline strategy. Pulls all customer meetings from the trailing quarter, cross-references CRM deal data (stage, amount, close date), scores deals on two axes: MEDDPICC for qualification depth and Deal Readiness Scorecard for close mechanics (tech win, legal, procurement, budget, CTA). Analyzes meeting momentum, and produces a prioritized close plan with per-deal strategies and next steps.

## Requirements
- The **Aircover Production** connector must be connected. All meeting and deal data comes from there.
- **Code execution / file creation** must be on (for charts and the output document).
- The host's Word-document creation capability and the `docx` JavaScript package must be available. If either is unavailable, explain the missing dependency and stop before rendering; do not install packages silently. The output is a .docx file with embedded charts so it opens cleanly in Google Drive, Word, and other editors.
- **Salesforce connector** is optional but recommended. When connected, provides a secondary validation that deals are still open and close dates fall within the quarter. Without it, the skill uses the CRM block from Aircover's get_deal (which mirrors SFDC fields).
- **Web search** is not required.

## Configuration
- Environment: Production (api.aircover.ai)
- App host: app.aircover.ai (for meeting links)
- CRM source: Aircover's get_deal returns a `crm` block with SFDC fields (sfdc_opportunity_name, sfdc_opportunity_id, amount, close date, stage). This is the primary CRM source. The Salesforce connector is a secondary validation layer only.

## Bundled resources
- `references/deal_readiness_scorecard.md` - the full Deal Readiness Scorecard agent spec with scoring rubrics, examples, and exclusion rules. Read this to understand what each DRS dimension means, how scores are assigned, and what the EXCLUDE lists say (critical for interpreting edge cases, especially Tech Win).

## Run order

### 1. Gather inputs from the user

Collect inputs in two rounds. Use tappable options where possible.

**Round 1: Agent selection**

Ask: "Before we start, how do you want to score your deals?"

Offer three options:
- **Use recommended agents** - "I will look for MEDDPICC (or BANT as a fallback) for qualification depth, and the Deal Readiness Scorecard for close mechanics."
- **Choose from your org's agents** - "I will show you the agents available in your Aircover account and you pick which ones to use."
- **Describe your own scoring** - "Tell me what dimensions you want to score deals on and I will build a custom rubric on the fly."

Store the selection as `agent_mode` ("recommended", "choose", "custom").

If `agent_mode` is "custom", ask a follow-up: "Describe the dimensions you want to evaluate each deal on. For example: 'champion strength, technical validation, budget status, urgency' or paste your methodology." Store as `custom_dimensions`. These will be used in step 6 to build a lightweight scoring rubric that ChatGPT applies manually from meeting notes (no Aircover agent needed).

**Round 2: Quota, timeline, and identity**

**a) Quarterly quota.** Ask: "What is your quota for this quarter?"
Offer tappable options: "$250K", "$500K", "$1,000,000", "Type my own"
If "Type my own", accept a dollar amount. Store as `quota_target`.

*

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 1 — file references are metadata, not package contents.

View saved version →

---
name: pre-call-prep
description: Generate a pre-call prep Word document for an upcoming meeting, pulling the last 2-4 transcripts from Aircover Production to build deal context, open action items, stakeholder priorities, landmines, and a suggested agenda. Use this whenever someone says "prep me for my call", "pre-call prep", "call prep for [company]", "get me ready for [meeting]", or wants a structured briefing doc before a customer meeting.
---

# Pre-Call Prep

Generate a polished pre-call prep .docx from Aircover Production data. Reads the last 2-4 transcripts for the deal, synthesizes open action items, stakeholder priorities, landmines, and objectives, and outputs a formatted Word document the rep can scan in five minutes before the call.

## Bundled resources
- `scripts/build_prep_doc.js` - generates the .docx from a structured JSON file (requires `docx` npm package).

Copy the script into your working directory before running:
```
cp "$SKILL_DIR/scripts/build_prep_doc.js" .
```
(`$SKILL_DIR` is the folder this SKILL.md is in.)

## Requirements
- The **Aircover Production** connector must be connected. All deal, meeting, and transcript data is read from there.
- **Code execution / file creation** must be on.
- Web search is used for company enrichment (org chart context, public facts).
- The `docx` JavaScript package must be available in the host runtime. If it is unavailable, explain the missing dependency and stop before rendering; do not install packages silently.

## Configuration
- Environment: Production (api.aircover.ai)
- App host: app.aircover.ai (for meeting links)
- Owner scoping: omit `owner` for org-wide, or pass the user's email for "my meetings." If unknown, ask once.

## Run order

### 1. Identify the deal and upcoming meeting
If the user names a company: `get_deals(search="company")`. Take the deal_key, prospect_org, deal_id, and nextMeetingDate. If the user names a date or "my next call": `list_meetings` over the relevant window, optionally scoped by `owner`.

Echo back the matched deal (company + next meeting date + stage) and confirm before proceeding.

### 2. Find the last 2-4 completed meetings for this deal
Use the `get_deal(prospect_org, deal_id)` response. It returns a `completed_meetings` array. Take the most recent 2-4 meetings (sorted newest first). If only 1-2 exist, use what is available.

If `completed_meetings` is missing or empty, fall back to `list_meetings` over a wide window (90 days back from the upcoming meeting) and filter by the deal's prospect_org in the meeting titles/attendees.

### 3. Pull meeting details and transcripts
For each completed meeting (most recent first):
- `get_meeting(meeting_id, include_previous_meeting_notes=true)` for attendees, notes, and prior-meeting notes.
- `get_meeting_transcript(meeting_id)` for the full transcript.

Start with the 2 most recent. Read both transcripts. If the content is thin (short calls, internal only, limited customer discussion), pull a 3rd or 4th. Stop at 4 max.

### 4. Pull deal and CRM context
`get_deal(prospect_org, deal_id)` returns a `crm` block. Extract:
- Opportunity amount, close date, stage (SFDC fields preferred, fall back to HubSpot).
- Any other CRM fields present (owner, account name).

Call `get_deal` once and reuse across all steps.

### 5. Check for qualification agents (optional enrichment)
`list_agents(category="qualification")`. If a qualification agent exists, run `get_qualification_results(deal_key, template_id)` to get deal-level qualification gaps. Use these to inform the "Objectives" and "What Matters Most" sections. If no qualification agent exists, skip silently.

### 6. Web enrichment (conservative)
If the company is a real, identifiable entity (not a test account), use web search for:
- Org chart context (who reports to whom, executive structure).
- Recent company news relevant to the deal.
- Contact titles and roles if not clear from transcripts.

Use only confident, exact-entity matches. If uncertai

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 5 — file references are metadata, not package contents.

View saved version →

---
name: product-sentiment-tracker
description: Generate a Customer Product Sentiment report as an Excel workbook from Aircover agent results. Runs the Product VoC agent on every external meeting in a date range, writes each result to disk as it goes, aggregates signals by account, and outputs a professional .xlsx with Sentiment Highlights, Account Summary, Signal Detail, Sentiment Summary, Raw Data, and Agent Properties Guide sheets. Trigger when the user says "product sentiment", "sentiment report", "VoC report", "product feedback report", "customer sentiment tracking", or asks for a summary of product signals across accounts.
---

# Product Sentiment Tracker

Generate a consolidated Customer Product Sentiment report from Aircover meeting data. Runs the Product VoC agent on every processable meeting, writes each result to a JSONL file on disk as it goes, then aggregates product requests, product gaps, feature adoption signals, competitive intelligence, integration requests, and VoC summaries by account. Output is a professionally formatted Excel workbook (.xlsx) where Raw Data is the source of truth and all other sheets aggregate from it.

## Bundled resources

- `scripts/generate_report.py`: Reads the JSONL results file, aggregates, and generates the .xlsx with six sheets (requires `openpyxl`).
- Follows the shared Aircover MCP rules (inlined below).

## Requirements

- The **Production** Aircover connector must be connected.
- Code execution / file creation enabled.

## Configuration

- **Environment:** Production (api.aircover.ai)
- **Agent:** Selected at run time, not hardcoded. The skill lists the available agents and asks the user which to run (see Run order step 2). It works best with a product-sentiment or product-VoC style agent whose properties cover requests, gaps, feature signals, competitive intelligence, integrations, and a summary.
- **App host:** app.aircover.ai (for meeting URLs)
- **Default date range:** Last 30 days from today
- **Default owner:** Omit (pull org-wide). Pass an email if the user asks for "my calls" only.

## Agent properties (expected shape)

A product-VoC agent typically returns these 6 properties. The agent the user selects may use different titles; **join on `title`, never on `key`** (keys are positional and vary), and map the selected agent's properties to the closest report slots below. A property with no equivalent can fold into the VoC Summary or be omitted. If the selected agent looks nothing like a product-sentiment agent, say so and confirm before running.

| # | Title | Scored | Max Score | What it captures |
|---|-------|--------|-----------|-----------------|
| 0 | Product Requests | Yes | 5 | Explicit feature requests from the customer |
| 1 | Product Gaps | Yes | 5 | Existing features that fall short of needs |
| 2 | Feature Adoption Signals | No | 0 | Customer reactions to specific features (Active Use, Interested, Not Adopted, Dropped) |
| 3 | Competitive Intelligence | No | 0 | Competitor mentions, comparisons, sentiment |
| 4 | Integration Requests | Yes | 5 | Integration needs for connecting to other systems |
| 5 | VoC Summary | No | 0 | 2-4 sentence executive summary of all signals |

**Important:** A single property result often contains multiple signals separated by double newlines (`\n\n`). Each block starting with a bold label (e.g., `**Request:**`, `**Gap:**`, `**Feature:**`, `**Competitor:**`, `**Integration:**`) is one individual signal. Parse these into separate rows on the Signal Detail sheet.

## Run order

### 1. Load tools and confirm environment

Use the Aircover tools exposed by the host and follow the exact parameter names in their live schemas. Confirm the connected MCP server is **Aircover Production** at `api.aircover.ai`. If the tools are unavailable, ask the user to connect Aircover.ai before continuing.

### 2. Interview (minimal)

First, **select the agent**. Call `list_agents` and present the available agents to the user (name and category), the

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 5 — file references are metadata, not package contents.